4DAnyone turns single monocular video into 4D human models

janusch_patas · x · 2026-08-21

4DAnyone turns a casual monocular video into a 4D Gaussian Splatting (4DGS) model without the need for camera rigs, calibration, or tripods. The project, accepted by SIGGRAPH Asia 2026, addresses consistency challenges using Reference Context Packing (RCP) and Target Context Routing (TCR), while leveraging a 3D skeleton for robust geometric conditioning.

Related event: 4DAnyone Reconstructs 4D Human Avatars from Monocular Video(2 posts)→

Original post →

More from Multimodal

Multimodal channel →